TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Qwen1.5

5 点作者 bratao超过 1 年前

2 条评论

reissbaker超过 1 年前
The price of intelligence is dropping to near-zero... An actually-open 72b model that benchmarks near GPT4 (Mistral Medium is still closed source / closed weights, even if an early version of it leaked with miqu) is insane. Even the 14b model easily outperforms gpt-3.5-turbo, and given how useful gpt-3.5-turbo finetunes are (they generally outperform non-finetuned GPT4 at a given task they've been finetuned on), I'd imagine the 14b model will prove pretty useful too as a super-low-cost finetuning target. Not to mention the fact that the 14b and especially 7b models are runnable locally on consumer GPUs...
wenyuanyu超过 1 年前
Wonder if the 0.5B model with int4 quant runs on my router...